Triple
T28572062
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | murder of William McKinley |
E723138
|
entity |
| Predicate | ledToVicePresidentBecomingPresident |
P165460
|
FINISHED |
| Object | Theodore Roosevelt |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Theodore Roosevelt | Statement: [murder of William McKinley, ledToVicePresidentBecomingPresident, Theodore Roosevelt]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ledToVicePresidentBecomingPresident Context triple: [murder of William McKinley, ledToVicePresidentBecomingPresident, Theodore Roosevelt]
-
A.
becamePresidentialOffice
Indicates that an entity assumed or transitioned into a presidential office or position.
-
B.
succeededAsVicePresidentBy
Indicates that one individual ceased serving as vice president and was followed in that office by another specific individual.
-
C.
presidentDuringVicePresidency
Indicates that one person served as president during the period when another person was serving as vice president.
-
D.
succeededByAsPresident
Indicates that one individual directly followed another in holding the office of president.
-
E.
servedAsVicePresidentFrom
Indicates that one entity held the position of vice president for another entity during a specified time period.
- F. None of above. chosen
Provenance (4 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69f01d7e97708190ae9e77ee66a68abd |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69f659355a208190be2609ffc7a9c427 |
completed | May 2, 2026, 8:06 p.m. |
| PD | Predicate disambiguation | batch_69f6575d89788190aca478e4aea05a65 |
completed | May 2, 2026, 7:58 p.m. |
| PDg | Predicate description generation | batch_69f65875030881909007c502b7dcc998 |
completed | May 2, 2026, 8:03 p.m. |
Created at: April 28, 2026, 4:10 a.m.